Affect Recognition in Muscular Response Signals

Abstract

This study investigated the potential of recognising arousal in motor activity collected by wristworn accelerometers. We hypothesise that emotional arousal emerges from the generalised central nervous system which embeds affective states within motor activity. We formulate arousal detection as a statistical problem of separating two sets -motor activity under emotional arousal and motor activity without arousal. We propose a novel test regime based on machine learning assuming that the two sets can be distinguished if a machine learning classifier can separate the sets better than random guessing. To increase the statistical power of the testing regime, the performance of the classifiers is evaluated in a cross-validation framework, and to test if the classifiers perform better than random guessing, a repeated cross-validation corrected t-test is used. The classifiers were evaluated on the basis of accuracy and Matthew's correlation coefficient. The suggested procedures were further compared against a traditional multivariate paired Hotelling's T-squared test. The classifiers achieved an accuracy of about 60%, and according to the proposed t-test were significantly better than random guessing. The suggested test regime demonstrated higher statistical power than Hotelling's T-squared test, and we conclude that we can distinguish between motor activity under emotional arousal and without it.

Early warning signals observed in motor activity preceding mood state change in bipolar disorder

“…However, according to the Nyquist–Shannon sampling theorem, the sampling rate needs to be twice the frequency of the original signal to obtain full resolution. 29 Consequently, with 10 Hz recordings, some information is lost, possibly causing a more fragmented stepwise CAC, reporting additional change points. In our case, the 10 Hz sampling frequency was chosen strictly to minimize the battery load and increase maximum recording time, ensuring study feasibility.…”

“…A technological study of accelerometer-equipped soccer supporters found significant differences between periods containing goals to non-event periods in the match, analyzing high resolution uncompressed actigraphy data. 29 Likewise, causality between fear and behavioral pattern changes have been observed in studies of laboratory mice. 28 This evidence supports the hypothesis proposed in a systematic review on activation in bipolar disorder; 5 namely, that motor activity can be considered an objective observation of the inner psychological state expressed in behavior patterns.…”